Heatmap Distribution Matching for Human Pose Estimation
- URL: http://arxiv.org/abs/2210.00740v2
- Date: Tue, 4 Oct 2022 01:47:57 GMT
- Title: Heatmap Distribution Matching for Human Pose Estimation
- Authors: Haoxuan Qu, Li Xu, Yujun Cai, Lin Geng Foo, Jun Liu
- Abstract summary: We show that optimizing the heatmap prediction in such a way, the model performance of body joint localization may not be consistently improved.
We propose to formulate the optimization of the heatmap prediction as a distribution matching problem between the predicted heatmap and the dot annotation of the body joint.
We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the MPII dataset.
- Score: 12.524484316923333
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: For tackling the task of 2D human pose estimation, the great majority of the
recent methods regard this task as a heatmap estimation problem, and optimize
the heatmap prediction using the Gaussian-smoothed heatmap as the optimization
objective and using the pixel-wise loss (e.g. MSE) as the loss function. In
this paper, we show that optimizing the heatmap prediction in such a way, the
model performance of body joint localization, which is the intrinsic objective
of this task, may not be consistently improved during the optimization process
of the heatmap prediction. To address this problem, from a novel perspective,
we propose to formulate the optimization of the heatmap prediction as a
distribution matching problem between the predicted heatmap and the dot
annotation of the body joint directly. By doing so, our proposed method does
not need to construct the Gaussian-smoothed heatmap and can achieve a more
consistent model performance improvement during the optimization of the heatmap
prediction. We show the effectiveness of our proposed method through extensive
experiments on the COCO dataset and the MPII dataset.
Related papers
- Differentially Private Optimization with Sparse Gradients [60.853074897282625]
We study differentially private (DP) optimization problems under sparsity of individual gradients.
Building on this, we obtain pure- and approximate-DP algorithms with almost optimal rates for convex optimization with sparse gradients.
arXiv Detail & Related papers (2024-04-16T20:01:10Z) - Exploiting Diffusion Prior for Generalizable Dense Prediction [85.4563592053464]
Recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate.
We introduce DMP, a pipeline utilizing pre-trained T2I models as a prior for dense prediction tasks.
Despite limited-domain training data, the approach yields faithful estimations for arbitrary images, surpassing existing state-of-the-art algorithms.
arXiv Detail & Related papers (2023-11-30T18:59:44Z) - Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation [71.24808323646167]
We propose textbfDiffusionPose, a new scheme for learning keypoints heatmaps by a neural network.
During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps.
Experiments show the prowess of our scheme with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets.
arXiv Detail & Related papers (2023-06-29T16:24:32Z) - Posterior temperature optimized Bayesian models for inverse problems in
medical imaging [59.82184400837329]
We present an unsupervised Bayesian approach to inverse problems in medical imaging using mean-field variational inference with a fully tempered posterior.
We show that an optimized posterior temperature leads to improved accuracy and uncertainty estimation.
Our source code is publicly available at calibrated.com/Cardio-AI/mfvi-dip-mia.
arXiv Detail & Related papers (2022-02-02T12:16:33Z) - Poseur: Direct Human Pose Regression with Transformers [119.79232258661995]
We propose a direct, regression-based approach to 2D human pose estimation from single images.
Our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints.
Ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
arXiv Detail & Related papers (2022-01-19T04:31:57Z) - Self-Supervision and Spatial-Sequential Attention Based Loss for
Multi-Person Pose Estimation [6.92027612631023]
Bottom-up based pose estimation approaches use heatmaps with auxiliary predictions to estimate joint positions and belonging at one time.
The lack of more explicit supervision results in low features utilization and contradictions between predictions in one model.
This paper proposes a new loss organization method which uses self-supervised heatmaps to reduce prediction contradictions and spatial-sequential attention to enhance networks' features extraction.
arXiv Detail & Related papers (2021-10-20T19:13:17Z) - Fast Scalable Image Restoration using Total Variation Priors and
Expectation Propagation [7.7731951589289565]
This paper presents a scalable approximate Bayesian method for image restoration using total variation (TV) priors.
We use the expectation propagation (EP) framework to approximate minimum mean squared error (MMSE) estimators and marginal (pixel-wise) variances.
arXiv Detail & Related papers (2021-10-04T17:28:41Z) - Entropic estimation of optimal transport maps [15.685006881635209]
We develop a method for estimating the optimal map between two distributions over $mathbbRd$ with rigorous finite-sample guarantees.
We show that our estimator is easy to compute using Sinkhorn's algorithm.
arXiv Detail & Related papers (2021-09-24T14:57:26Z) - Improving Robustness for Pose Estimation via Stable Heatmap Regression [19.108116394510258]
A heatmap regression method is proposed to alleviate network vulnerability to small perturbations.
A maximum stability training loss is used to simplify the optimization difficulty.
The proposed method achieves a significant advance in robustness over state-of-the-art approaches on two benchmark datasets.
arXiv Detail & Related papers (2021-05-08T03:07:05Z) - Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box
Optimization Framework [100.36569795440889]
This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information.
We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
arXiv Detail & Related papers (2020-12-21T17:29:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.